CN112417299A - Webpage recommendation method, computer storage medium and computing device - Google Patents
Webpage recommendation method, computer storage medium and computing device Download PDFInfo
- Publication number
- CN112417299A CN112417299A CN202011422838.1A CN202011422838A CN112417299A CN 112417299 A CN112417299 A CN 112417299A CN 202011422838 A CN202011422838 A CN 202011422838A CN 112417299 A CN112417299 A CN 112417299A
- Authority
- CN
- China
- Prior art keywords
- user
- search
- webpage
- item
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a webpage recommendation method, a computer storage medium and a computing device. The webpage recommendation method comprises the following steps: receiving a search keyword input by a user; judging whether the search keyword is a polysemous word; if yes, obtaining all meaning items of the search keyword; determining a weight value of each semantic item related webpage content expected by the user according to the attribute of the user; recommending the webpage for the user according to the weight value of the webpage content related to each semantic item expected by the user. The scheme of the invention can determine the weight value of the webpage content related to each meaning item of the search keyword expected by the user according to the attribute of the user, and further recommend the related webpage for the user according to the weight value of the webpage content related to each meaning item, so that the webpage content recommended in the search result is more in line with the search requirement of the user, and the satisfaction degree of the user is improved.
Description
Technical Field
The invention relates to the technical field of internet, in particular to a webpage recommendation method, a computer storage medium and a computing device.
Background
With the development and popularization of internet technology, web page search has almost become a necessary way for modern people to obtain information in work and life. In the traditional web page search, a server carries out web page recommendation of related contents according to specific search terms input by a user. With the increasing of the number of users, the search volume of the world per day has reached about 500 hundred million times, how to recommend content meeting the user requirements to the users has become the research focus of each big search company, and various search algorithms are in endless. However, due to the regional differences of languages (such as differences between different countries) and the difference of meanings, the same search term may have two or more different meanings, and the meanings (or referred to as search intentions) of the same search term focused by different types of users are different, so that the general search algorithm cannot accurately distinguish the search intentions of the different types of users, and the recommended web page content does not meet the user requirements, or the content required by the user is buried in many search results and is difficult to obtain quickly. Therefore, how to recommend the desired content to the user when the search term has two or more different meanings and facilitate the user to find the desired effective information in the various contents becomes a technical problem to be solved in the field.
Disclosure of Invention
In view of the above, there is provided a web page recommendation method, computer storage medium, and computing device that overcome or at least partially address the above-mentioned problems.
An object of the present invention is to provide a web page recommendation method capable of performing web page recommendation according to attributes of a user to improve user satisfaction when the user searches ambiguous words.
A further object of the present invention is to further improve user satisfaction of a web page by recommending the web page according to at least one attribute of user age, user occupation, user historical search behavior, user habit search behavior, and relevance of current time to each meaning item of a search keyword.
Another further object of the present invention is to reduce the time for the user to remove redundant information and improve the efficiency of the user to obtain valid information.
Particularly, according to an aspect of an embodiment of the present invention, there is provided a web page recommendation method including:
receiving a search keyword input by a user;
judging whether the search keyword is a polysemous word;
if yes, obtaining all meaning items of the search keyword;
determining a weight value of each semantic item related webpage content expected by the user according to the attribute of the user;
recommending the webpage for the user according to the weight value of the webpage content related to each semantic item expected by the user.
Optionally, the attribute of the user comprises at least one of:
user age, user occupation, user historical search behavior, user habit search behavior, and a correlation of current time to each of the meaning items.
Optionally, the step of determining, according to the attribute of the user, a weight value of each semantic item-related web content desired by the user includes:
determining a weight factor of webpage content related to each semantic item expected by the user corresponding to each attribute according to each attribute of the user;
and for each meaning item, adding the weight factors of the webpage content related to the meaning item expected by the user and corresponding to the attributes to obtain the weight value of the webpage content related to the meaning item expected by the user.
Optionally, when the attribute of the user includes a user age, the step of determining, according to the attributes of the user, a weighting factor of web page content related to each semantic item desired by the user corresponding to each attribute includes:
determining an age stage in which the age of the user is;
and determining a weight factor of each semantic item related webpage content expected by the user corresponding to the age of the user according to the determined age stage and a pre-established corresponding relation between the age stage and the weight factor.
Optionally, when the attribute of the user includes a user occupation, the step of determining, according to the attributes of the user, a weighting factor of web content related to each semantic item desired by the user corresponding to each attribute includes:
determining the occupation of the user according to the registration information of the user or the daily search content of the user;
and determining a weight factor of webpage content related to each semantic item expected by the user and corresponding to the occupation of the user according to the occupation of the user and a pre-established corresponding relation between the occupation of the user and the weight factor.
Optionally, when the attribute of the user includes a user history search behavior, the step of determining, according to the attributes of the user, a weighting factor of web page content related to each semantic item desired by the user and corresponding to each attribute includes:
acquiring the browsing times of the user to the webpage content related to each semantic item in at least one historical search performed by the user according to the search keyword;
and determining the weight factor of each semantic item related webpage content expected by the user corresponding to the historical search behavior of the user according to the browsing times of the user on each semantic item related webpage content.
Optionally, when the attribute of the user includes a user habit search behavior, the step of determining, according to the attributes of the user, a weighting factor of web page content related to each semantic item desired by the user and corresponding to each attribute includes:
determining a category of web page content viewed in at least one search history of the user prior to a current search;
and determining a weight factor of webpage content related to each meaning item expected by the user and corresponding to the habit search behavior of the user according to the determined relevance between the category of the webpage content browsed by the user and each meaning item.
Optionally, the step of recommending a web page for the user according to the weight value of each semantic item related web page content desired by the user includes:
determining the proportion of the content of each semantic item related webpage in the front appointed number of pages in the search result according to the weight value of each semantic item related webpage expected by the user;
generating a search result page according to the ratio of the webpage content related to each semantic item in the determined front appointed number of pages;
and displaying the search result page to recommend a webpage for the user.
According to another aspect of the embodiments of the present invention, there is also provided a computer storage medium storing computer program code, which, when run on a computing device, causes the computing device to execute the web page recommendation method according to any one of the preceding.
According to still another aspect of the embodiments of the present invention, there is also provided a computing device including:
a processor; and
a memory storing computer program code;
the computer program code, when executed by the processor, causes the computing device to perform the web page recommendation method of any of the preceding claims.
According to the webpage recommendation method provided by the embodiment of the invention, when the search keyword input by the user is determined to be the polysemous word, the weighted value of the webpage content related to each meaning item of the search keyword expected by the user can be determined according to the attribute of the user, and further, the related webpage is recommended for the user according to the weighted value of the webpage content related to each meaning item, so that the webpage content recommended in the search result is more in line with the search requirement of the user, and the satisfaction degree of the user is improved.
Furthermore, the embodiment of the invention calculates the weight value of the webpage content related to each meaning item expected by the user according to the weight factor determined by at least one attribute of the user age, the user occupation, the user historical search behavior, the user habit search behavior and the relevance of each meaning item of the search keyword, thereby further improving the user satisfaction of the webpage recommended based on the weight value.
Furthermore, the embodiment of the invention determines the proportion of the content of the webpage related to each meaning item in the page of the search result according to the weight value of the content of the webpage related to each meaning item expected by the user, thereby reducing the time for the user to remove redundant information and improving the efficiency for the user to obtain effective information.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
The above and other objects, advantages and features of the present invention will become more apparent to those skilled in the art from the following detailed description of specific embodiments thereof, taken in conjunction with the accompanying drawings.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flowchart illustrating a web page recommendation method according to an embodiment of the invention;
FIG. 2 is a flowchart illustrating steps of determining a weight value of each meaning item-related web content desired by a user according to an attribute of the user according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a web page recommendation method according to another embodiment of the present invention;
FIG. 4 shows a schematic structural diagram of a computing device according to an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
In the prior art, for a search word of a polysemous word type (i.e. a word entry having two or more different meanings), the search intentions of users of different categories cannot be accurately distinguished by the existing search algorithm, so that the recommended web page content does not meet the user requirements, and the user cannot easily and quickly obtain the effective information desired by the user. For example, the search term "apple" encompasses both the meaning of fruit apples and the meaning of apple electronics, and is thus an ambiguous word. When searching for an "apple", in the search results displayed by the existing search engine (e.g., a hundredth search engine), the advanced recommended web pages are basically all apple electronic product related web pages, but for fruit growers or other users who want to obtain information about fruits and apples, these are only invalid information, and they need to pull down the pages or even turn pages to find the related web pages about the fruits and apples, so that the users need to spend too much time to remove the cumbersome invalid information to find the contents they want in the tedious and massive information, and the user experience is not good.
In order to solve the above technical problem, an embodiment of the present invention provides a web page recommendation method. Fig. 1 is a flowchart illustrating a web page recommendation method according to an embodiment of the present invention. Referring to fig. 1, the method may include at least the following steps S102 to S110.
Step S102, receiving a search keyword input by a user.
Step S104, judging whether the search keyword is a polysemous word. If yes, go to step S106.
Step S106, obtaining each meaning item of the search keyword.
And S108, determining the weight value of the webpage content related to each meaning item expected by the user according to the attribute of the user.
And step S110, recommending a webpage for the user according to the weight value of the webpage content related to each meaning item expected by the user.
According to the webpage recommendation method provided by the embodiment of the invention, when the search keyword input by the user is determined to be the polysemous word, the weighted value of the webpage content related to each meaning item of the search keyword expected by the user can be determined according to the attribute of the user, and further, the related webpage is recommended for the user according to the weighted value of the webpage content related to each meaning item, so that the webpage content recommended in the search result is more in line with the search requirement of the user, and the satisfaction degree of the user is improved.
In step S102, the user refers to a user of a terminal (e.g., a desktop computer, a mobile phone, a tablet computer, etc.), and the search keyword may be input by the user through a search box of the search page, or may be input in other manners, such as voice input, which is not limited in the present invention.
In the above step S104, it may be determined whether the search keyword is an ambiguous word by matching the search keyword with a pre-established ambiguous word table. The word list includes a plurality of entries having two or even more different meanings. And if the search keyword is matched with a certain entry in the polysemous word list, determining that the search keyword is a polysemous word. Otherwise, determining that the search keyword is not an ambiguous word, and ending the process.
After determining that the search keyword is a polysemous word, step S106 is executed to obtain each semantic item of the search keyword. In one embodiment, the semantic items of the entries may be recorded in the aforementioned polysemous table, and the semantic items of the entries matching the search keyword are read from the polysemous table in step S106. In another embodiment, a correspondence table between each entry in the polysemous table and a plurality of semantic items thereof may be established in advance, and each semantic item of the entry matching the search keyword is read from the correspondence table in step S106.
In step S108 above, the attributes of the user may include at least one of the following items: user age, user occupation, user historical search behavior, user habit search behavior, relevance of current time to each meaning item, and the like.
Further, as shown in fig. 2, step S108 may be embodied as the following steps:
step S202, according to each item of attribute of the user, determining the weight factor of the webpage content related to each meaning item expected by the user corresponding to each item of attribute.
Step S204, for each meaning item, adding the weight factors of the relevant webpage content of the meaning item expected by the user corresponding to the attributes to obtain the weight value of the relevant webpage content of the meaning item expected by the user, thereby obtaining the weight value of the relevant webpage content of the meaning item expected by the user. The summation here may be arithmetic summation or weighted summation, and the present invention is not limited to this.
For example, assuming that the attributes of the user include three items of user age, user occupation, and user historical search behavior, for a search keyword "apple" having two items of significance a (fruit apple) and significance B (apple electronic product), first, a weight factor (not called weight factor a1) of the user-desired meaning item a-related web content and a weight factor (not called weight factor B1) of the meaning item B-related web content corresponding to the user age attribute are determined, a weight factor (not called weight factor a2) of the user-desired meaning item a-related web content and a weight factor (not called weight factor B2) of the meaning item B-related web content corresponding to the user occupation attribute, and a weight factor (not called weight factor a3) of the user-desired meaning item a-related web content and a weight factor (not called weight factor B2) of the meaning item B-related web content corresponding to the user historical search behavior attribute are determined Sub b 3). Then, the weight factor a1, the weight factor a2 and the weight factor a3 are added to obtain the weight value of the webpage content related to the meaning item A expected by the user; and adding the weight factor B1, the weight factor B2 and the weight factor B3 to obtain the weight value of the webpage content related to the meaning item B expected by the user.
The following describes a method for determining a weight factor of web page content related to each meaning item of a search keyword desired by a user corresponding to each attribute according to each attribute of the user.
(1) Age of the user
When the attribute of the user comprises the age of the user, firstly determining the age stage of the age of the user, and then determining the weight factor of the webpage content related to each meaning item of the search keyword expected by the user corresponding to the age of the user according to the determined age stage and the pre-established corresponding relation between the age stage and the weight factor.
For example, the age stages may be divided as follows, and the weighting factor values of the respective age stages are set, thereby establishing the correspondence relationship between the age stages and the weighting factors. The search keyword "apple" is still used as an example below.
A. 0-10 years old: users at this age stage are mainly in the cognitive stage of the existing world, and when searching for apples, it can be basically determined that 80% of the users are likely to know apples in the fruit. Therefore, the weighting factor of the webpage content related to the semantic item a (fruit apple) corresponding to the age stage is set to 0.8, and the weighting factor of the webpage content related to the semantic item B (apple electronic product) is set to 0.2.
B. 10-20 years old: users at this age stage are mainly looking for world novelty, and when searching for apples, it can be determined that 60% of them may want to know apples in fruits, and 40% of them want to know functions related to apple electronic products (e.g., iphone). Therefore, the weighting factor of the webpage content related to the semantic item a (fruit apple) corresponding to the age stage is set to 0.6, and the weighting factor of the webpage content related to the semantic item B (apple electronic product) is set to 0.4.
C. 20-30 years old: users at this age are mainly post-graduate workers, and when searching for apples in general, it can be determined that 40% of the users may want to know apples in fruits, and 60% of the users may want to know related enterprises or histories of apple electronic products. Therefore, the weighting factor of the webpage content related to the semantic item a (fruit apple) corresponding to the age stage is set to 0.4, and the weighting factor of the webpage content related to the semantic item B (apple electronic product) is set to 0.6.
D. 30-40 years old: users at this age may want to know about apples in fruit in 50% and apple electronics related businesses or history or even their IOS operating systems in 50% when searching for apples. Therefore, the weighting factor of the webpage content related to the semantic item a (fruit apple) corresponding to the age stage is set to 0.5, and the weighting factor of the webpage content related to the semantic item B (apple electronic product) is set to 0.5.
E. 40-50 years old: users at this age may want to know about apples in fruit in 40% and apple electronics related businesses or history or even their IOS operating systems in 60% when searching for apples. Therefore, the weighting factor of the webpage content related to the semantic item a (fruit apple) corresponding to the age stage is set to 0.4, and the weighting factor of the webpage content related to the semantic item B (apple electronic product) is set to 0.6.
F. 50-60 years old: users at this age may want to know about apples in fruit in 40% and apple electronics related businesses or history or even their IOS operating systems in 60% when searching for apples. Therefore, the weighting factor of the webpage content related to the semantic item a (fruit apple) corresponding to the age stage is set to 0.4, and the weighting factor of the webpage content related to the semantic item B (apple electronic product) is set to 0.6.
G. 60-70 years old: users at this age may want to know some nutritional information about the apples in the fruit 60% and apple electronics related businesses or history or even their IOS operating systems 40% when searching for apples. Therefore, the weighting factor of the webpage content related to the semantic item a (fruit apple) corresponding to the age stage is set to 0.6, and the weighting factor of the webpage content related to the semantic item B (apple electronic product) is set to 0.4.
H. 70-80 years old: users at this age may want to know some nutritional information about the apples in the fruit 60% and apple electronics related businesses or history or even their IOS operating systems 40% when searching for apples. Therefore, the weighting factor of the webpage content related to the semantic item a (fruit apple) corresponding to the age stage is set to 0.6, and the weighting factor of the webpage content related to the semantic item B (apple electronic product) is set to 0.4.
I. 80-90 years old: users at this age may want to know some nutritional information about the apples in the fruit in 70% and apple electronics related businesses or history or even their IOS operating systems in 30% when searching for apples. Therefore, the weighting factor of the webpage content related to the semantic item a (fruit apple) corresponding to the age stage is set to 0.7, and the weighting factor of the webpage content related to the semantic item B (apple electronic product) is set to 0.3.
J. After the age of 90 years: users at this age may want to know some nutritional information about the apples in the fruit 80% and apple electronics related businesses or history or even their IOS operating systems 20% when searching for apples. Therefore, the weighting factor of the webpage content related to the semantic item a (fruit apple) corresponding to the age stage is set to 0.8, and the weighting factor of the webpage content related to the semantic item B (apple electronic product) is set to 0.2.
It should be noted that the above age classification and setting of the weighting factors are only exemplary, and in practical applications, the setting may be specifically performed according to practical application situations, and the present invention is not limited to this.
(2) User occupation
When the attribute of the user comprises the occupation of the user, the occupation of the user is determined according to the registration information of the user or daily search content of the user, and then the weight factor of webpage content related to each meaning item of a search keyword expected by the user corresponding to the occupation of the user is determined according to the occupation of the user and the pre-established corresponding relation between the occupation of the user and the weight factor.
User professions (which may also be referred to as identity categories) may include, for example, farmers, program development engineers, artists, financial, legal, and the like. The user occupation can be filled in when the user registers, and can also be determined by analyzing daily search contents of the user history. For example, if the historical search records of the user are analyzed to obtain that the daily search content of the user is mainly fruit information, the occupation of the user can be determined as fruit growers; if the related content of the operating system is taken as the main content, the occupation of the user can be determined as a program development engineer; if the literature and art information is taken as the main information, the occupation of the user can be determined as the artist.
Still taking the search keyword "apple" as an example, how to determine the weight factor of the web page content related to each meaning item of the search keyword desired by the user according to the user occupation is described below. For an ambiguous word entry 'apple', presetting a weight factor of a webpage content related to a semantic item A (fruit apple) corresponding to a fruit grower to be 0.8, and presetting a weight factor of a webpage content related to a semantic item B (apple electronic product) to be 0.2; the weight factor of the webpage content related to the semantic item A (fruit apple) corresponding to the program development engineer is 0.4, and the weight factor of the webpage content related to the semantic item B (apple electronic product) is 0.6; the weighting factor of the webpage content related to the semantic item A (fruit apple) corresponding to the artist is 0.6, and the weighting factor of the webpage content related to the semantic item B (apple electronic product) corresponding to the artist is 0.4. When searching for the apple, if the occupation of the user is determined to be fruit growers, determining that the weight factor of the webpage content related to the meaning item A corresponding to the occupation of the user is 0.8 and the weight factor of the webpage content related to the meaning item B is 0.2 according to the corresponding relation.
(3) User historical search behavior
When the attribute of the user comprises the historical search behavior of the user, the browsing times of the user to the webpage content related to each meaning item of the search keyword in at least one historical search performed by the user by using the search keyword are firstly obtained, and then the weight factor of the webpage content related to each meaning item expected by the user and corresponding to the historical search behavior of the user is determined according to the browsing times of the user to the webpage content related to each meaning item.
In a specific embodiment, the weight factor of the web page content related to each meaning item of the search keyword may be determined according to the browsing times of the web page content related to each meaning item of the search keyword when the user searches with the search keyword last time. Still taking the search keyword "apple" as an example, if the number of times of browsing related pages of fruits and apples in the previous search by the user is more, it indicates that the apple which the user is most interested in is eaten, and therefore, the weight factor of the related webpage content of the meaning item a can be determined to be a first weight factor value (e.g. 0.9) according to the historical search behavior of the user, and the weight factor of the related webpage content of the meaning item B is determined to be a second weight factor value (e.g. 0.1).
In another specific embodiment, the weight factor of the web page content related to each meaning item of the search keyword may be determined according to the browsing times of the web page content related to each meaning item of the search keyword in a plurality of (e.g., 5) historical searches performed by the user with the search keyword. For example, in the first 5 "apple" searches, the user browses more times the webpage sold by the apple phone, which indicates that the user is more interested in apple electronic products, so that the weight factor of the webpage content related to the meaning item a can be determined to be a third weight factor value (e.g. 0.2), and the weight factor of the webpage content related to the meaning item B can be determined to be a fourth weight factor value (e.g. 0.8) according to the historical search behavior of the user.
(4) User habit search behavior
When the attribute of the user comprises the habit search behavior of the user, firstly, determining the category of the webpage content browsed in at least one search history record of the user before current search, and then determining the weight factor of the webpage content related to each meaning item expected by the user corresponding to the habit search behavior of the user according to the determined relevance between the category of the webpage content browsed by the user and each meaning item.
In a specific embodiment, the weight factor of the web page content related to each meaning item of the keyword of the search may be determined according to the relevance between the category of the web page content browsed in the previous search performed by the user and each meaning item of the keyword of the search. Still taking the search keyword "apple" as an example, if it is determined by analysis that the webpage content mainly browsed by the user in the previous search is related to fruit categories (such as oranges, sugar cane, bananas, etc.), according to the relevance between the fruit categories and the meaning item a and the meaning item B of the "apple", the weight factor of the webpage content related to the meaning item a corresponding to the habit search behavior of the user may be determined to be a fifth weight factor value (such as 0.8), and the weight factor of the webpage content related to the meaning item B is determined to be a sixth weight factor value (such as 0.2).
In another specific implementation, the weighting factor of the web page content related to each meaning item of the keyword of the search may be determined according to the relevance between the category of the web page content browsed in the multiple search history of the user before the search and each meaning item of the keyword of the search. The number of times of searching the history in this embodiment is preferably a category that sufficiently represents the user's habit concerns, and may be, for example, ten thousands of times. Still taking the search keyword "apple" as an example, if it is determined by analysis that the web page content browsed in the search history of the last ten thousand times of the user is mainly related to the technology category, according to the relevance between the technology category and the meaning item a and the meaning item B of the "apple", it may be determined that the weight factor of the web page content related to the meaning item a corresponding to the habit search behavior of the user is the seventh weight factor value (e.g., 0.4), and the weight factor of the web page content related to the meaning item B is the eighth weight factor value (e.g., 0.6).
(5) Relevance of current time to semantic items of search keywords
The current time (also referred to as the current time interval) may affect the user's search intent to some extent, e.g., if the current time happens to be in a fruit production time interval, the user may be more inclined to learn about fruit-related information, and if the current time is in the middle or immediately before an economic or social event occurs, the user may be more inclined to learn about the event-related information. Therefore, the relevance between the current time and each meaning item of the search keyword can be taken as one of the consideration factors of webpage recommendation, and the weight factor of the webpage content related to each meaning item expected by the user can be determined according to the relevance between the current time and each meaning item of the search keyword.
Taking the search keyword "apple" as an example, if the current time is exactly the time of apple production, and a large number of apples refresh the view of people in terms of price or features in the international or current environment, the weight factor of the webpage content related to the meaning item a may be determined to be a ninth weight factor value (e.g., 0.7) and the weight factor of the webpage content related to the meaning item B may be determined to be a tenth weight factor value (e.g., 0.3) according to the relevance between the current time and the meaning item a and the meaning item B of the "apple". If the current time is exactly the beginning of the latest mobile phone release of the apple, and the latest mobile phone of the apple is a trending topic, the weight factor of the webpage content related to the meaning item a can be determined to be the eleventh weight factor value (such as 0.3) and the weight factor of the webpage content related to the meaning item B can be determined to be the twelfth weight factor value (such as 0.7) according to the relevance between the current time and the meaning item a and the meaning item B of the apple.
According to the embodiment of the invention, the weight value of the webpage content related to each meaning item expected by the user is calculated by the weight factor determined by at least one attribute of the user age, the user occupation, the user historical search behavior, the user habit search behavior and the relevance of each meaning item of the search keyword, so that the user satisfaction of the webpage recommended based on the weight value is further improved.
In step S110, there may be a plurality of ways to recommend the web page according to the weight value of the web page content related to each meaning item desired by the user. For example, the weight values of the web page contents related to the meaning items may be compared, and the web page contents related to the meaning item with the largest weight value may be preferentially recommended in the search result, specifically, the web page contents related to the meaning item with the largest weight value may be displayed in the most front designated page number of the search result, so as to achieve the purpose of preferential recommendation. Of course, other recommended presentation manners may be adopted, which are not listed herein.
In a specific embodiment, the web page recommendation may be made by:
firstly, determining the proportion of the web page contents related to each meaning item in the front appointed number of pages in the search result according to the weight value of the web page contents related to each meaning item expected by the user.
The ratio of the percentage of the web content related to each meaning item in the page to the weight value of the web content related to each meaning item may be a direct proportion relationship, or may be a preset correspondence relationship (for example, the percentage of the high weight value is directly set to 90%, and the percentage of the low weight value is set to 10%), and the present invention is not particularly limited. For example, assuming that the weighted value of the webpage content related to the "apple" meaning item a desired by the user is 0.8, and the weighted value of the webpage content related to the "apple" meaning item B is 3.2, the percentage of the webpage content related to the meaning item a in the top specified number (e.g., 3) of pages in the search result is determined to be 80%, and the percentage of the webpage content related to the meaning item B is determined to be 20%.
And then, generating a search result page according to the determined proportion of the webpage content related to each meaning item in the front appointed number of pages.
And finally, displaying the search result page to recommend a webpage for the user.
In practical application, the web page content in the page after the specified number of pages can be displayed according to the search result obtained by the existing search algorithm.
According to the embodiment of the invention, the proportion of the content of the webpage related to each meaning item in the page of the search result is determined according to the weight value of the content of the webpage related to each meaning item expected by the user, so that the time for the user to remove redundant information is reduced, and the efficiency for the user to obtain effective information is improved. Meanwhile, besides the webpage content related to the meaning item with the largest weight value, the webpage content related to other meaning items with certain proportions is reserved in the front page, so that a user can conveniently obtain the related information of other meaning items when needed, and the user experience is better.
It should be noted that, although only the search keyword "apple" with two meaning terms is taken as an example in the present application, search keywords with three or more meaning terms may also be performed in a similar manner, and are not described again herein.
In the above, various implementation manners of each link of the embodiment shown in fig. 1 are introduced, and an implementation process of the web page recommendation method of the present invention will be described in detail through a specific embodiment.
Fig. 3 is a flowchart illustrating a web page recommendation method according to an embodiment of the present invention. Referring to fig. 3, the method may include the following steps S302 to S314.
Step S302, receiving a search keyword input by a user.
Specifically, in this embodiment, the input search keyword is "apple".
Step S304, judging whether the search keyword is a polysemous word. If yes, go to step S306.
In this step, a search is performed in a pre-established polysemous word list to find the entry "apple" matching the input search keyword "apple", and the input search keyword is determined to be a polysemous word.
Step S306, obtaining each meaning item of the search keyword.
In this step, a semantic item a (fruit apple) and a semantic item B (apple electronic product) of "apple" are obtained from a correspondence table of each entry and a plurality of semantic items thereof, which is established in advance.
Step S308, determining weight factors of webpage contents related to each meaning item expected by the user corresponding to each item of the user according to the attributes of the user, wherein the attributes of the user comprise the age of the user, the occupation of the user, historical search behaviors of the user, habit search behaviors of the user and the relevance between the current time and each meaning item.
In this embodiment, assuming that the age of the user is 38 years, the occupation is a program development engineer, the apple which is most interested in the historical search behavior is eaten, the content which is determined to be interested by the user in the habit search behavior is a science and technology category, and the current time is the beginning of the release of the iphone, according to the method described above, the weight factors of the web page content related to the meaning item a corresponding to the age of the user, the occupation of the user, the historical search behavior of the user, the habit search behavior of the user, and the association between the current time and each meaning item are determined to be 0.5, 0.2, 0.4, 0.3, and 0.4, and the weight factors of the web page content related to the meaning item B are determined to be 0.5, 0.8, 0.6, 0.7, and 0.6.
Step S310, for each meaning item, adding the weight factors of the relevant webpage content of the meaning item expected by the user corresponding to the attributes to obtain the weight value of the relevant webpage content of the meaning item expected by the user, thereby obtaining the weight value of the relevant webpage content of the meaning item expected by the user.
In this step, the weight value of the content of the relevant web page of the meaning item a expected by the user is calculated to be 0.5+0.2+0.4+0.3+0.4 ═ 1.8, and the weight value of the content of the relevant web page of the meaning item B is calculated to be 0.5+0.8+0.6+0.7+0.6 ═ 3.2.
Step S312, according to the weight value of the web page content related to each meaning item expected by the user, determining the proportion of the web page content related to each meaning item in the front appointed number of pages in the search result.
In this step, the weight values of the web contents related to the two meaning items are compared, and it is determined that the percentage of the web contents related to the meaning item a having a large weight value in the first 3 pages of the search result is 80%, and the percentage of the web contents related to the meaning item B is 20%.
And step S314, generating a search result page according to the determined proportion of the webpage content related to each meaning item in the front appointed number of pages, and displaying the generated search result page to recommend a webpage for the user.
According to the embodiment, the webpage can be recommended according to the attribute of the user, the user satisfaction degree of the webpage is improved, the operation of discharging redundant information by the user is reduced, and the user time is saved.
Based on the same inventive concept, the embodiment of the invention also provides a computer storage medium. The computer storage medium stores computer program code which, when run on a computing device, causes the computing device to perform the method of web page recommendation of any of the embodiments or combination of embodiments above.
Based on the same inventive concept, the embodiment of the invention also provides the computing equipment. FIG. 4 shows a schematic block diagram of a computing device 100, according to an embodiment of the invention. The computing device 100 includes a processor 110 and a memory 120. The memory 120 stores computer program code. The computer program code, when executed by the processor 110, causes the computing device 100 to perform the method of web page recommendation of any embodiment or combination of embodiments hereinbefore.
According to any one or a combination of multiple optional embodiments, the embodiment of the present invention can achieve the following advantages:
according to the webpage recommendation method provided by the embodiment of the invention, when the search keyword input by the user is determined to be the polysemous word, the weighted value of the webpage content related to each meaning item of the search keyword expected by the user can be determined according to the attribute of the user, and further, the related webpage is recommended for the user according to the weighted value of the webpage content related to each meaning item, so that the webpage content recommended in the search result is more in line with the search requirement of the user, and the satisfaction degree of the user is improved.
Furthermore, the embodiment of the invention calculates the weight value of the webpage content related to each meaning item expected by the user according to the weight factor determined by at least one attribute of the user age, the user occupation, the user historical search behavior, the user habit search behavior and the relevance of each meaning item of the search keyword, thereby further improving the user satisfaction of the webpage recommended based on the weight value.
Furthermore, the embodiment of the invention determines the proportion of the content of the webpage related to each meaning item in the page of the search result according to the weight value of the content of the webpage related to each meaning item expected by the user, thereby reducing the time for the user to remove redundant information and improving the efficiency for the user to obtain effective information.
It is clear to those skilled in the art that the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and for the sake of brevity, further description is omitted here.
In addition, the functional units in the embodiments of the present invention may be physically independent of each other, two or more functional units may be integrated together, or all the functional units may be integrated in one processing unit. The integrated functional units may be implemented in the form of hardware, or in the form of software or firmware.
Those of ordinary skill in the art will understand that: the integrated functional units, if implemented in software and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computing device (e.g., a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention when the instructions are executed. And the aforementioned storage medium includes: u disk, removable hard disk, Read Only Memory (ROM), Random Access Memory (RAM), magnetic or optical disk, and other various media capable of storing program code.
Alternatively, all or part of the steps of implementing the foregoing method embodiments may be implemented by hardware (such as a computing device, e.g., a personal computer, a server, or a network device) associated with program instructions, which may be stored in a computer-readable storage medium, and when the program instructions are executed by a processor of the computing device, the computing device executes all or part of the steps of the method according to the embodiments of the present invention.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments can be modified or some or all of the technical features can be equivalently replaced within the spirit and principle of the present invention; such modifications or substitutions do not depart from the scope of the present invention.
Claims (10)
1. A method for recommending a web page, comprising:
receiving a search keyword input by a user;
judging whether the search keyword is a polysemous word;
if yes, obtaining all meaning items of the search keyword;
determining a weight value of each semantic item related webpage content expected by the user according to the attribute of the user;
recommending the webpage for the user according to the weight value of the webpage content related to each semantic item expected by the user.
2. The web page recommendation method according to claim 1, wherein the user's attribute comprises at least one of:
user age, user occupation, user historical search behavior, user habit search behavior, and a correlation of current time to each of the meaning items.
3. The method for recommending web pages according to claim 2, wherein the step of determining the weight value of each content of web pages related to said semantic item desired by said user according to the attribute of said user comprises:
determining a weight factor of webpage content related to each semantic item expected by the user corresponding to each attribute according to each attribute of the user;
and for each meaning item, adding the weight factors of the webpage content related to the meaning item expected by the user and corresponding to the attributes to obtain the weight value of the webpage content related to the meaning item expected by the user.
4. The method according to claim 3, wherein when the attribute of the user includes a user age, the step of determining a weighting factor of the web page content related to each of the semantic items desired by the user corresponding to each of the attributes according to each of the attributes of the user comprises:
determining an age stage in which the age of the user is;
and determining a weight factor of each semantic item related webpage content expected by the user corresponding to the age of the user according to the determined age stage and a pre-established corresponding relation between the age stage and the weight factor.
5. The method for recommending web pages according to claim 3, wherein when the attributes of the user include user occupation, the step of determining the weight factor of the web page content related to each semantic item desired by the user corresponding to each attribute according to each attribute of the user comprises:
determining the occupation of the user according to the registration information of the user or the daily search content of the user;
and determining a weight factor of webpage content related to each semantic item expected by the user and corresponding to the occupation of the user according to the occupation of the user and a pre-established corresponding relation between the occupation of the user and the weight factor.
6. The method for recommending web pages according to claim 3, wherein when the attributes of the user include historical search behavior of the user, the step of determining the weighting factors of the web page contents related to the semantic items desired by the user corresponding to the attributes of the user according to the attributes of the user comprises:
acquiring the browsing times of the user to the webpage content related to each semantic item in at least one historical search performed by the user according to the search keyword;
and determining the weight factor of each semantic item related webpage content expected by the user corresponding to the historical search behavior of the user according to the browsing times of the user on each semantic item related webpage content.
7. The method for recommending web pages according to claim 3, wherein when the attributes of the user include user habit search behavior, the step of determining the weighting factor of the web page content related to each of the meaning items desired by the user corresponding to each of the attributes according to each of the attributes of the user comprises:
determining a category of web page content viewed in at least one search history of the user prior to a current search;
and determining a weight factor of webpage content related to each meaning item expected by the user and corresponding to the habit search behavior of the user according to the determined relevance between the category of the webpage content browsed by the user and each meaning item.
8. The method for recommending web pages according to claim 3, wherein the step of recommending web pages for the user according to the weight value of each content of the web pages related to the semantic item desired by the user comprises:
determining the proportion of the content of each semantic item related webpage in the front appointed number of pages in the search result according to the weight value of each semantic item related webpage expected by the user;
generating a search result page according to the ratio of the webpage content related to each semantic item in the determined front appointed number of pages;
and displaying the search result page to recommend a webpage for the user.
9. A computer storage medium storing computer program code which, when run on a computing device, causes the computing device to perform a web page recommendation method according to any one of claims 1-8.
10. A computing device, comprising:
a processor; and
a memory storing computer program code;
the computer program code, when executed by the processor, causes the computing device to perform the web page recommendation method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011422838.1A CN112417299A (en) | 2020-12-08 | 2020-12-08 | Webpage recommendation method, computer storage medium and computing device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011422838.1A CN112417299A (en) | 2020-12-08 | 2020-12-08 | Webpage recommendation method, computer storage medium and computing device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112417299A true CN112417299A (en) | 2021-02-26 |
Family
ID=74775252
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011422838.1A Pending CN112417299A (en) | 2020-12-08 | 2020-12-08 | Webpage recommendation method, computer storage medium and computing device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112417299A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117076773A (en) * | 2023-08-23 | 2023-11-17 | 上海兰桂骐技术发展股份有限公司 | Data source screening and optimizing method based on internet information |
| CN117076773B (en) * | 2023-08-23 | 2024-05-28 | 上海兰桂骐技术发展股份有限公司 | Data source screening and optimizing method based on internet information |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101286175A (en) * | 2008-05-09 | 2008-10-15 | 北京大学 | File presentation method and its system based on label |
| CN102063453A (en) * | 2010-05-31 | 2011-05-18 | 百度在线网络技术（北京）有限公司 | Method and device for searching based on demands of user |
| CN103488741A (en) * | 2013-09-22 | 2014-01-01 | 华东师范大学 | Online semantic excavation system of Chinese polysemic words and based on uniform resource locator (URL) |
| CN106294730A (en) * | 2016-08-09 | 2017-01-04 | 百度在线网络技术（北京）有限公司 | The recommendation method and device of information |
| CN108509499A (en) * | 2018-02-27 | 2018-09-07 | 北京三快在线科技有限公司 | A kind of searching method and device, electronic equipment |
| CN109190049A (en) * | 2018-11-02 | 2019-01-11 | 北京字节跳动网络技术有限公司 | Keyword recommendation method, system, electronic equipment and computer-readable medium |
| CN111177523A (en) * | 2018-11-09 | 2020-05-19 | 阿里巴巴集团控股有限公司 | Webpage recommendation method and device, electronic equipment and computer readable medium |
-
2020
- 2020-12-08 CN CN202011422838.1A patent/CN112417299A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101286175A (en) * | 2008-05-09 | 2008-10-15 | 北京大学 | File presentation method and its system based on label |
| CN102063453A (en) * | 2010-05-31 | 2011-05-18 | 百度在线网络技术（北京）有限公司 | Method and device for searching based on demands of user |
| CN103488741A (en) * | 2013-09-22 | 2014-01-01 | 华东师范大学 | Online semantic excavation system of Chinese polysemic words and based on uniform resource locator (URL) |
| CN106294730A (en) * | 2016-08-09 | 2017-01-04 | 百度在线网络技术（北京）有限公司 | The recommendation method and device of information |
| CN108509499A (en) * | 2018-02-27 | 2018-09-07 | 北京三快在线科技有限公司 | A kind of searching method and device, electronic equipment |
| CN109190049A (en) * | 2018-11-02 | 2019-01-11 | 北京字节跳动网络技术有限公司 | Keyword recommendation method, system, electronic equipment and computer-readable medium |
| CN111177523A (en) * | 2018-11-09 | 2020-05-19 | 阿里巴巴集团控股有限公司 | Webpage recommendation method and device, electronic equipment and computer readable medium |
Non-Patent Citations (1)
| Title |
|---|
| 张甫 等: "基于用户信息需求的网页相关性评价研究", 情报理论与实践, vol. 34, no. 05, pages 30 - 33 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117076773A (en) * | 2023-08-23 | 2023-11-17 | 上海兰桂骐技术发展股份有限公司 | Data source screening and optimizing method based on internet information |
| CN117076773B (en) * | 2023-08-23 | 2024-05-28 | 上海兰桂骐技术发展股份有限公司 | Data source screening and optimizing method based on internet information |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8838438B2 (en) | System and method for determining sentiment from text content | |
| US20190197122A1 (en) | Method and device for generating review article of hot news, and terminal device | |
| US9235646B2 (en) | Method and system for a search engine for user generated content (UGC) | |
| WO2018014759A1 (en) | Method, device and system for presenting clustering data table | |
| US9299028B2 (en) | Identifying suggestive intent in social posts | |
| US20150046371A1 (en) | System and method for determining sentiment from text content | |
| WO2011080899A1 (en) | Information recommendation method | |
| CN107193987B (en) | Method, device and system for acquiring search terms related to page | |
| US9785704B2 (en) | Extracting query dimensions from search results | |
| US20140379719A1 (en) | System and method for tagging and searching documents | |
| US20090177651A1 (en) | Information processing device and method, program, and recording medium | |
| CN109241451B (en) | Content combination recommendation method and device and readable storage medium | |
| WO2014206151A1 (en) | System and method for tagging and searching documents | |
| CN106682049B (en) | Topic display system and topic display method | |
| KR20160042896A (en) | Browsing images via mined hyperlinked text snippets | |
| CN111061954B (en) | Search result sorting method and device and storage medium | |
| CN111639255B (en) | Recommendation method and device for search keywords, storage medium and electronic equipment | |
| Ahlgren | Research on sentiment analysis: the first decade | |
| US10901992B2 (en) | System and method for efficiently handling queries | |
| US20160299951A1 (en) | Processing a search query and retrieving targeted records from a networked database system | |
| CN108763369B (en) | Video searching method and device | |
| CN105468649A (en) | Method and apparatus for determining matching of to-be-displayed object | |
| EP2189917A1 (en) | Facilitating display of an interactive and dynamic cloud with advertising and domain features | |
| Sathick et al. | A generic framework for extraction of knowledge from social web sources (social networking websites) for an online recommendation system | |
| CN116401459A (en) | Internet information processing method, system and recording medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |